Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    5 minutes or disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    批量
    0.46
    ert
    0.44
    いません
    0.43
    gye
    0.42
    thew
    0.42
     convexo
    0.42
    गिर
    0.42
    法施行
    0.41
    ｎ
    0.41
    स्
    0.41
    POSITIVE LOGITS
     разных
    0.51
     Edith
    0.48
    фан
    0.45
     Rhodes
    0.43
    rma
    0.43
     Oatmeal
    0.43
     Anita
    0.42
     Revolutionary
    0.42
    чнее
    0.42
     Bitte
    0.42
    Act Density 0.004%

    No Known Activations